ME

Meltemi 7B Instruct v1

MeltemiGGUF by SPAHEUpdated 2024-04-17
Download on Hugging Face
Parameters7.48B
Context32K
Layers32
Architecturellama
Smallest quant3.3 GB
Quick answer

Meltemi 7B Instruct v1 needs about 6.1 GB of memory at Q4_K_M (a 4.5 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 6 quants, from 3.3 GB (Q3_K_S) to 29.9 GB (F32). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

Meltemi 7B Instruct v1 is a 7.48B-parameter Meltemi model in GGUF format, quantized by SPAHE. Its trained context length is 32K tokens. The repository has 6 quant files, from 3.3 GB (Q3_K_S) to 29.9 GB (F32).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K_S3.3 GB 4.9 GB
Fits Get file →
Q4_K_M4.5 GB 6.1 GB
Fits Get file →
Q6_K6.1 GB 7.7 GB
Tight Get file →
Q8_08.0 GB 9.5 GB
Too big Get file →
F1615.0 GB 16.5 GB
Too big Get file →
F3229.9 GB 31.5 GB
Too big Get file →

What GPU do you need for Meltemi 7B Instruct v1?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: no quant fits at an 8K context.
  • 6 GB VRAM: the best quant that fits is Q3_K_S (3.3 GB file, about 4.9 GB in use).
  • 8 GB VRAM: the best quant that fits is Q6_K (6.1 GB file, about 7.7 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (8.0 GB file, about 9.5 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (8.0 GB file, about 9.5 GB in use).
  • 24 GB VRAM: the best quant that fits is F16 (15.0 GB file, about 16.5 GB in use).
  • 32 GB VRAM: the best quant that fits is F32 (29.9 GB file, about 31.5 GB in use).

Which Meltemi 7B Instruct v1 quant should you choose?

Q4_K_M is the usual starting point for Meltemi 7B Instruct v1: it balances file size and quality well. Here it is a 4.5 GB file.

The Q8_0 file is 8.0 GB, about 1.8 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is Q3_K_S at 3.3 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters7.48B
Layers32
Trained context32,768 tokens
KV cache (fp16)128 KB per token

Source

Quantized bySPAHE
FamilyMeltemi
Licenseapache-2.0
Downloads (HF)109
Last updated2024-04-17

Frequently asked questions about Meltemi 7B Instruct v1

How much VRAM does Meltemi 7B Instruct v1 need?

About 6.1 GB at Q4_K_M with an 8K context window. That is the 4.5 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run Meltemi 7B Instruct v1 on an 8 GB GPU?

Yes, with Q6_K: the 6.1 GB file needs about 7.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Meltemi 7B Instruct v1 GGUF?

It depends on the quant: Q3_K_S is 3.3 GB, Q4_K_M is 4.5 GB, Q6_K is 6.1 GB, Q8_0 is 8.0 GB, F16 is 15.0 GB, F32 is 29.9 GB.

What context length does Meltemi 7B Instruct v1 support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.

Where can I download Meltemi 7B Instruct v1 GGUF?

The files are on Hugging Face in the SPAHE/Meltemi-7B-Instruct-v1-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Meltemi 7B Instruct v1 use?

Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Other GGUFs of Meltemi-7B-Instruct-v1

Similar models

Browse all →

More Meltemi models

All Meltemi →

Other small models

All small models →